Parameter-Efficient Fine-Tuning with Culturally-Aligned Adapters for Cross-Lingual Transfer in Nigerian Low-Resource Languages

Taiwo Timothy Oluwagbenga, Mamudu Francis Itanyi
Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, PMLR 319:293-305, 2026.

Abstract

This paper introduces CulturalAdapt, a Parameter-Efficient Fine-Tuning (PEFT) framework adding Low-Rank Adaptation (LoRA) modules to language adapters grounded in Nigerian cultural and linguistic context. CulturalAdapt separates language-specific adaptation (tonal patterns, diacritics, code-switching, morphological structure) from task-specific fine-tuning. Evaluated on NaijaSenti, MasakhaNER 2.0, and AfriSenti, CulturalAdapt achieves state-of-the-art macro-F1 of 77.3 on NER, 79.0 on sentiment analysis, and 84.1 on cross-lingual sentiment transfer, using only 2.1% of trainable parameters and reducing peak GPU memory by $3.4\times$ relative to full fine-tuning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v319-oluwagbenga26a, title = {Parameter-Efficient Fine-Tuning with Culturally-Aligned Adapters for Cross-Lingual Transfer in {Nigerian} Low-Resource Languages}, author = {Oluwagbenga, Taiwo Timothy and Itanyi, Mamudu Francis}, booktitle = {Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments}, pages = {293--305}, year = {2026}, editor = {Folorunso, Sakinat and Ogundokun, Roseline and Oladipo, Francisca}, volume = {319}, series = {Proceedings of Machine Learning Research}, month = {11--14 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v319/main/assets/oluwagbenga26a/oluwagbenga26a.pdf}, url = {https://proceedings.mlr.press/v319/oluwagbenga26a.html}, abstract = {This paper introduces CulturalAdapt, a Parameter-Efficient Fine-Tuning (PEFT) framework adding Low-Rank Adaptation (LoRA) modules to language adapters grounded in Nigerian cultural and linguistic context. CulturalAdapt separates language-specific adaptation (tonal patterns, diacritics, code-switching, morphological structure) from task-specific fine-tuning. Evaluated on NaijaSenti, MasakhaNER 2.0, and AfriSenti, CulturalAdapt achieves state-of-the-art macro-F1 of 77.3 on NER, 79.0 on sentiment analysis, and 84.1 on cross-lingual sentiment transfer, using only 2.1% of trainable parameters and reducing peak GPU memory by $3.4\times$ relative to full fine-tuning.} }
Endnote
%0 Conference Paper %T Parameter-Efficient Fine-Tuning with Culturally-Aligned Adapters for Cross-Lingual Transfer in Nigerian Low-Resource Languages %A Taiwo Timothy Oluwagbenga %A Mamudu Francis Itanyi %B Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments %C Proceedings of Machine Learning Research %D 2026 %E Sakinat Folorunso %E Roseline Ogundokun %E Francisca Oladipo %F pmlr-v319-oluwagbenga26a %I PMLR %P 293--305 %U https://proceedings.mlr.press/v319/oluwagbenga26a.html %V 319 %X This paper introduces CulturalAdapt, a Parameter-Efficient Fine-Tuning (PEFT) framework adding Low-Rank Adaptation (LoRA) modules to language adapters grounded in Nigerian cultural and linguistic context. CulturalAdapt separates language-specific adaptation (tonal patterns, diacritics, code-switching, morphological structure) from task-specific fine-tuning. Evaluated on NaijaSenti, MasakhaNER 2.0, and AfriSenti, CulturalAdapt achieves state-of-the-art macro-F1 of 77.3 on NER, 79.0 on sentiment analysis, and 84.1 on cross-lingual sentiment transfer, using only 2.1% of trainable parameters and reducing peak GPU memory by $3.4\times$ relative to full fine-tuning.
APA
Oluwagbenga, T.T. & Itanyi, M.F.. (2026). Parameter-Efficient Fine-Tuning with Culturally-Aligned Adapters for Cross-Lingual Transfer in Nigerian Low-Resource Languages. Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, in Proceedings of Machine Learning Research 319:293-305 Available from https://proceedings.mlr.press/v319/oluwagbenga26a.html.

Related Material